Skip to main content
skill CX Codex

aggregating-crypto-news — Claude Code skill

aggregating-crypto-news — a skill for Claude Code and five other platforms that pulls articles from CoinDesk, CoinTelegraph, The Block, and Decrypt RSS feeds, then filters by coin, category, and time window.

MIT 238 installs ★ 2,935 updated 2026-11-01

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add jeremylongshore/tons-of-skills-marketplace --skill aggregating-crypto-news -a claude-code
Open on GitHub

What aggregating-crypto-news does

The skill calls news_aggregator.py, which fetches RSS feeds, drops undated and future-dated items, and scores the rest from 0 to 100 based on market-moving keywords, source authority, and recency.

Filters go in as CLI arguments: --coin BTC, --category defi, --period 4h, --top 20, --min-score 70. Output is a ranked table with source, headline, age, and score. The meta.feed_health field records per-source parse counts, window matches, undated items, and the latest publication timestamp. When a feed fails, the script logs the reason — HTTP error, timeout, or bad XML — then continues with whatever sources remain.

Python 3.8+ and three packages are required before the first run: pip install feedparser requests pyyaml. The source registry lives in ${CLAUDE_SKILL_DIR}/config/sources.yaml, including disabled feeds with their dates and reasons.

What it helps with

  • pull the latest BTC or ETH headlines from multiple sources at once
  • filter DeFi announcements across CoinDesk, CoinTelegraph, The Block, and Decrypt
  • export ranked results to JSON for downstream processing
  • diagnose which RSS feeds failed and why
  • surface only high-relevance articles by setting a minimum score

Example prompts for the agent

  • Fetch the top 20 crypto news items from the past 24 hours
  • Get ETH news in the defi category for the last 4 hours
  • Run the aggregator with --coin BTC --period 4h and save output to news.json

How to install aggregating-crypto-news

1Skills CLI (Vercel)

npx skills add jeremylongshore/tons-of-skills-marketplace --skill aggregating-crypto-news -a claude-code

2Manually: put the files in place

~/.claude/skills/aggregating-crypto-news/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/aggregating-crypto-news/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about aggregating-crypto-news

How do I install aggregating-crypto-news in Claude Code?

Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill aggregating-crypto-news -a claude-code. The skill will be available at ~/.claude/skills/aggregating-crypto-news/SKILL.md.

What does the aggregating-crypto-news skill do?

It fetches RSS feeds from CoinDesk, CoinTelegraph, The Block, and Decrypt, filters articles by coin symbol, category, and time window, then ranks them by a relevance score from 0 to 100.

What do I need before running this skill?

Python 3.8+ and three packages installed via pip install feedparser requests pyyaml. An active internet connection is also required to reach the RSS feeds.

Source text

SKILL.md · MIT
---
name: aggregating-crypto-news
description: 'Aggregate cryptocurrency news from configured RSS sources including CoinDesk,
  CoinTelegraph, The Block, and Decrypt.

  Use when needing to monitor crypto market news, track announcements, or find coin-specific
  updates.

  Trigger with phrases like "get crypto news", "latest Bitcoin headlines", "DeFi announcements",
  "scan for breaking news", or "check crypto updates".

  '
allowed-tools: Read, Bash(python:*)
version: 1.27.0
author: Jeremy Longshore <[email protected]>
license: MIT
tags:
  - crypto
  - monitoring
  - aggregating-crypto
compatibility: Designed for Claude Code
---

# Aggregating Crypto News

## Overview

Fetch configured RSS feeds on demand, filter dated articles by coin/category and UTC time window, and rank them using keyword and recency scores. Source availability and coverage vary; the tool reports failed and disabled feeds rather than implying every source was checked successfully.

## Prerequisites

The user prepares the Python environment before invoking this skill.

1. **Python 3.8+** installed
2. **Dependencies**: `pip install feedparser requests pyyaml`
3. Internet connectivity for RSS feed access

## Instructions

1. **Assess user intent** - determine filters needed:
   - General news: no filters, use defaults
   - Coin-specific: extract symbol (BTC, ETH, etc.)
   - Category-specific: extract category (defi, nft, regulatory, etc.)
   - Time-specific: extract window (1h, 4h, 24h, 7d)

2. **Run the aggregator** with appropriate filters:

   ```bash
   # Default scan (top 20, past 24h, relevance sorted)
   python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py

   # Coin-specific scan
   python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coin BTC --period 4h

   # Category filter
   python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --category defi --top 30

   # Multiple filters
   python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coin ETH --category defi --period 24h --top 15
   ```

3. **Export results** for downstream processing:

   ```bash
   python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --format json --output news.json
   ```

4. **Present results** to the user:
   - Show source, title, age, and relevance score
   - Highlight market-moving keywords if present
   - Provide links for full articles
   - Summarize configured/disabled, fetched/failed sources and articles found
   - Report feed failures, including when other feeds return matching articles
   - A zero-match query is distinct from an all-feed failure (exit 1)
   - JSON `meta.feed_health` records per-source parsed/window/undated counts and latest publication; CSV keeps diagnostics on stderr
   - Undated and future-dated items are excluded from the requested time window

## Output

Table showing articles ranked by relevance score (0-100) based on market-moving keyword detection, source authority, and recency:

```text
CRYPTO NEWS AGGREGATOR — [generated UTC time]
[rank] [source] [headline] [age] [score]
Summary: [shown] articles | [attempted] sources | [matched] matches
Feed health: [fetched] fetched | [failed] failed | [disabled] disabled
[source]: failed — [HTTP/timeout/parse reason, when applicable]
```

This is a layout example, not a record of actual headlines or coverage. RSS
publication dates govern the time window, not fetch time or a claimed live scan.
The registry retains disabled URLs and dated reasons for review; re-enable a
source only after checking its current feed and any publisher usage terms.

## Error Handling

| Error           | Cause                | Solution                                                |
| --------------- | -------------------- | ------------------------------------------------------- |
| Network timeout | RSS feed unreachable | Uses valid, unexpired cache; reports failures otherwise |
| Parse error     | Malformed RSS        | Skips entry; continues with valid articles              |
| No results      | Filters too strict   | Inspect feed health before suggesting relaxed filters   |
| Invalid coin    | Unknown symbol       | List similar valid symbols                              |

Use Read to inspect [`references/errors.md`](references/errors.md) for comprehensive error handling.

## Examples

Filtering patterns for common news monitoring scenarios:

```bash
# Latest crypto news (defaults)
python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py

# Bitcoin news from past 4 hours
python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coin BTC --period 4h

# DeFi category news
python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --category defi

# High-relevance news only
python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --min-score 70 --top 10

# Multiple coins
python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coins BTC,ETH,SOL
```

## Resources

- [`references/implementation.md`](references/implementation.md) - CLI options, categories, JSON format, advanced filtering
- [`references/errors.md`](references/errors.md) - Comprehensive error handling
- [`references/examples.md`](references/examples.md) - Detailed usage examples
- `${CLAUDE_SKILL_DIR}/config/sources.yaml` - Full source registry
- CoinDesk RSS: https://www.coindesk.com/arc/outboundfeeds/rss/
- feedparser docs: https://feedparser.readthedocs.io/

© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace

Similar skills

All skills for Finance and business →

From the same set139

The whole set →
readme-generator Writes README files on its own once you mention readme generator or readme in a prompt. It walks through the steps and produces configs along the way. CX Codex +1 273installs n8n-workflow-generator n8n-workflow-generator generates production-ready configurations and steps for n8n automation flows. Activates whenever you mention n8n in your assistant prompt. CX Codex +1 271installs consul-service-discovery Automates Consul service discovery workflows and writes production configs. Triggers automatically on service discovery queries. CX Codex +1 251installs swagger-doc-creator swagger-doc-creator automates Swagger and OpenAPI documentation tasks, generating schema configurations and validating API definitions against standard patterns. CX Codex +1 239installs forecasting-time-series-data forecasting-time-series-data is a Claude Code skill that predicts future values from historical time series. It activates for tasks such as estimating sales or website traffic over time. CX Codex +1 206installs mermaid-flowchart-generator mermaid-flowchart-generator — a skill that gives an agent step-by-step guidance for Mermaid flowchart work. It activates on its own when the prompt mentions mermaid. CX Codex +1 174installs vertex-infra-expert vertex-infra-expert — a skill for provisioning Vertex AI infrastructure via Terraform. Deploys Gemini endpoints, vector search indices, ML pipelines, and production AI services with encryption, auto-scaling, and least-privilege IAM. CX Codex +1 154installs plantuml-diagram-generator plantuml-diagram-generator automates creating PlantUML diagrams and visual documentation. It triggers automatically whenever you mention PlantUML or diagram generation in your prompt. CX Codex +1 123installs

Project sponsors

Companies that keep this analytics open